Removes an image from a slide
AI agents call delete_image to permanently remove resources in Keynote MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting an image from a slide is a destructive operation; once removed, the image is gone from the slide and cannot be recovered without an undo action or backup. This fits the Destructive category as it irreversibly removes data. Severity is medium because it affects a single image within a presentation rather than the entire file.
From the tool's definition "Removes an image from a slide" — the word 'removes' indicates irreversible deletion of content from a presentation.
Attacks that exploit this kind of access
Removes an image from a slide. It is categorised as a Destructive tool in the Keynote MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Keynote MCP Server MCP server in PolicyLayer and add a rule for delete_image: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Keynote MCP Server. Nothing to install.
delete_image is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_image rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for delete_image. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
delete_image is provided by the Keynote MCP Server MCP server (superdwayne/keynotemp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →